1
|
|
|
<?php |
2
|
|
|
namespace PHPHtmlParser\Dom; |
3
|
|
|
|
4
|
|
|
use PHPHtmlParser\Exceptions\CircularException; |
5
|
|
|
use PHPHtmlParser\Exceptions\ParentNotFoundException; |
6
|
|
|
use PHPHtmlParser\Exceptions\ChildNotFoundException; |
7
|
|
|
use PHPHtmlParser\Selector; |
8
|
|
|
use stringEncode\Encode; |
9
|
|
|
use PHPHtmlParser\Finder; |
10
|
|
|
|
11
|
|
|
/** |
12
|
|
|
* Dom node object. |
13
|
|
|
* |
14
|
|
|
* @property string outerhtml |
15
|
|
|
* @property string innerhtml |
16
|
|
|
* @property string text |
17
|
|
|
* @property \PHPHtmlParser\Dom\Tag tag |
18
|
|
|
* @property InnerNode parent |
19
|
|
|
*/ |
20
|
|
|
abstract class AbstractNode |
21
|
|
|
{ |
22
|
|
|
private static $count = 0; |
23
|
|
|
/** |
24
|
|
|
* Contains the tag name/type |
25
|
|
|
* |
26
|
|
|
* @var \PHPHtmlParser\Dom\Tag |
27
|
|
|
*/ |
28
|
|
|
protected $tag; |
29
|
|
|
|
30
|
|
|
/** |
31
|
|
|
* Contains a list of attributes on this tag. |
32
|
|
|
* |
33
|
|
|
* @var array |
34
|
|
|
*/ |
35
|
|
|
protected $attr = []; |
36
|
|
|
|
37
|
|
|
/** |
38
|
|
|
* Contains the parent Node. |
39
|
|
|
* |
40
|
|
|
* @var InnerNode |
41
|
|
|
*/ |
42
|
|
|
protected $parent = null; |
43
|
|
|
|
44
|
|
|
/** |
45
|
|
|
* The unique id of the class. Given by PHP. |
46
|
|
|
* |
47
|
|
|
* @var string |
48
|
|
|
*/ |
49
|
|
|
protected $id; |
50
|
|
|
|
51
|
|
|
/** |
52
|
|
|
* The encoding class used to encode strings. |
53
|
|
|
* |
54
|
|
|
* @var mixed |
55
|
|
|
*/ |
56
|
|
|
protected $encode; |
57
|
|
|
|
58
|
|
|
/** |
59
|
|
|
* Creates a unique id for this node. |
60
|
|
|
*/ |
61
|
453 |
|
public function __construct() |
62
|
|
|
{ |
63
|
453 |
|
$this->id = self::$count; |
|
|
|
|
64
|
453 |
|
self::$count++; |
65
|
453 |
|
} |
66
|
|
|
|
67
|
|
|
/** |
68
|
|
|
* Magic get method for attributes and certain methods. |
69
|
|
|
* |
70
|
|
|
* @param string $key |
71
|
|
|
* @return mixed |
72
|
|
|
*/ |
73
|
171 |
|
public function __get(string $key) |
74
|
|
|
{ |
75
|
|
|
// check attribute first |
76
|
171 |
|
if ( ! is_null($this->getAttribute($key))) { |
77
|
39 |
|
return $this->getAttribute($key); |
78
|
|
|
} |
79
|
141 |
|
switch (strtolower($key)) { |
80
|
141 |
|
case 'outerhtml': |
81
|
33 |
|
return $this->outerHtml(); |
82
|
108 |
|
case 'innerhtml': |
83
|
54 |
|
return $this->innerHtml(); |
84
|
57 |
|
case 'text': |
85
|
51 |
|
return $this->text(); |
86
|
6 |
|
case 'tag': |
87
|
3 |
|
return $this->getTag(); |
88
|
3 |
|
case 'parent': |
89
|
|
|
return $this->getParent(); |
90
|
|
|
} |
91
|
|
|
|
92
|
3 |
|
return null; |
93
|
|
|
} |
94
|
|
|
|
95
|
|
|
/** |
96
|
|
|
* Attempts to clear out any object references. |
97
|
|
|
*/ |
98
|
126 |
|
public function __destruct() |
99
|
|
|
{ |
100
|
126 |
|
$this->tag = null; |
101
|
126 |
|
$this->attr = []; |
102
|
126 |
|
$this->parent = null; |
103
|
126 |
|
$this->children = []; |
|
|
|
|
104
|
126 |
|
} |
105
|
|
|
|
106
|
|
|
/** |
107
|
|
|
* Simply calls the outer text method. |
108
|
|
|
* |
109
|
|
|
* @return string |
110
|
|
|
*/ |
111
|
6 |
|
public function __toString() |
112
|
|
|
{ |
113
|
6 |
|
return $this->outerHtml(); |
114
|
|
|
} |
115
|
|
|
|
116
|
|
|
/** |
117
|
|
|
* Reset node counter |
118
|
|
|
* |
119
|
|
|
* @return void |
120
|
|
|
*/ |
121
|
144 |
|
public static function resetCount() |
122
|
|
|
{ |
123
|
144 |
|
self::$count = 0; |
124
|
144 |
|
} |
125
|
|
|
|
126
|
|
|
/** |
127
|
|
|
* Returns the id of this object. |
128
|
|
|
* |
129
|
|
|
* @return int |
130
|
|
|
*/ |
131
|
387 |
|
public function id(): int |
132
|
|
|
{ |
133
|
387 |
|
return $this->id; |
134
|
|
|
} |
135
|
|
|
|
136
|
|
|
/** |
137
|
|
|
* Returns the parent of node. |
138
|
|
|
* |
139
|
|
|
* @return AbstractNode |
140
|
|
|
*/ |
141
|
198 |
|
public function getParent() |
142
|
|
|
{ |
143
|
198 |
|
return $this->parent; |
144
|
|
|
} |
145
|
|
|
|
146
|
|
|
/** |
147
|
|
|
* Sets the parent node. |
148
|
|
|
* |
149
|
|
|
* @param InnerNode $parent |
150
|
|
|
* @return AbstractNode |
151
|
|
|
* @throws CircularException |
152
|
|
|
* @chainable |
153
|
|
|
*/ |
154
|
381 |
|
public function setParent(InnerNode $parent): AbstractNode |
155
|
|
|
{ |
156
|
|
|
// remove from old parent |
157
|
381 |
|
if ( ! is_null($this->parent)) { |
158
|
30 |
|
if ($this->parent->id() == $parent->id()) { |
159
|
|
|
// already the parent |
160
|
27 |
|
return $this; |
161
|
|
|
} |
162
|
|
|
|
163
|
6 |
|
$this->parent->removeChild($this->id); |
164
|
|
|
} |
165
|
|
|
|
166
|
381 |
|
$this->parent = $parent; |
167
|
|
|
|
168
|
|
|
// assign child to parent |
169
|
381 |
|
$this->parent->addChild($this); |
170
|
|
|
|
171
|
381 |
|
return $this; |
172
|
|
|
} |
173
|
|
|
|
174
|
|
|
/** |
175
|
|
|
* Removes this node and all its children from the |
176
|
|
|
* DOM tree. |
177
|
|
|
* |
178
|
|
|
* @return void |
179
|
|
|
*/ |
180
|
3 |
|
public function delete() |
181
|
|
|
{ |
182
|
3 |
|
if ( ! is_null($this->parent)) { |
183
|
3 |
|
$this->parent->removeChild($this->id); |
184
|
|
|
} |
185
|
3 |
|
$this->parent->clear(); |
186
|
3 |
|
$this->clear(); |
187
|
3 |
|
} |
188
|
|
|
|
189
|
|
|
/** |
190
|
|
|
* Sets the encoding class to this node. |
191
|
|
|
* |
192
|
|
|
* @param Encode $encode |
193
|
|
|
* @return void |
194
|
|
|
*/ |
195
|
186 |
|
public function propagateEncoding(Encode $encode) |
196
|
|
|
{ |
197
|
186 |
|
$this->encode = $encode; |
198
|
186 |
|
$this->tag->setEncoding($encode); |
199
|
186 |
|
} |
200
|
|
|
|
201
|
|
|
/** |
202
|
|
|
* Checks if the given node id is an ancestor of |
203
|
|
|
* the current node. |
204
|
|
|
* |
205
|
|
|
* @param int $id |
206
|
|
|
* @return bool |
207
|
|
|
*/ |
208
|
384 |
|
public function isAncestor(int $id): Bool |
209
|
|
|
{ |
210
|
384 |
|
if ( ! is_null($this->getAncestor($id))) { |
211
|
6 |
|
return true; |
212
|
|
|
} |
213
|
|
|
|
214
|
384 |
|
return false; |
215
|
|
|
} |
216
|
|
|
|
217
|
|
|
/** |
218
|
|
|
* Attempts to get an ancestor node by the given id. |
219
|
|
|
* |
220
|
|
|
* @param int $id |
221
|
|
|
* @return null|AbstractNode |
222
|
|
|
*/ |
223
|
387 |
|
public function getAncestor(int $id) |
224
|
|
|
{ |
225
|
387 |
|
if ( ! is_null($this->parent)) { |
226
|
267 |
|
if ($this->parent->id() == $id) { |
227
|
12 |
|
return $this->parent; |
228
|
|
|
} |
229
|
|
|
|
230
|
258 |
|
return $this->parent->getAncestor($id); |
231
|
|
|
} |
232
|
|
|
|
233
|
387 |
|
return null; |
234
|
|
|
} |
235
|
|
|
|
236
|
|
|
/** |
237
|
|
|
* Checks if the current node has a next sibling. |
238
|
|
|
* |
239
|
|
|
* @return bool |
240
|
|
|
*/ |
241
|
9 |
|
public function hasNextSibling(): bool |
242
|
|
|
{ |
243
|
|
|
try |
244
|
|
|
{ |
245
|
9 |
|
$sibling = $this->nextSibling(); |
|
|
|
|
246
|
|
|
// sibling found, return true; |
247
|
9 |
|
return true; |
248
|
|
|
} |
249
|
9 |
|
catch (ParentNotFoundException $e) |
250
|
|
|
{ |
251
|
|
|
// no parent, no next sibling |
252
|
|
|
return false; |
253
|
|
|
} |
254
|
9 |
|
catch (ChildNotFoundException $e) |
255
|
|
|
{ |
256
|
|
|
// no sibling found |
257
|
9 |
|
return false; |
258
|
|
|
} |
259
|
|
|
} |
260
|
|
|
|
261
|
|
|
/** |
262
|
|
|
* Attempts to get the next sibling. |
263
|
|
|
* |
264
|
|
|
* @return AbstractNode |
265
|
|
|
* @throws ParentNotFoundException |
266
|
|
|
*/ |
267
|
39 |
|
public function nextSibling(): AbstractNode |
268
|
|
|
{ |
269
|
39 |
|
if (is_null($this->parent)) { |
270
|
3 |
|
throw new ParentNotFoundException('Parent is not set for this node.'); |
271
|
|
|
} |
272
|
|
|
|
273
|
36 |
|
return $this->parent->nextChild($this->id); |
274
|
|
|
} |
275
|
|
|
|
276
|
|
|
/** |
277
|
|
|
* Attempts to get the previous sibling |
278
|
|
|
* |
279
|
|
|
* @return AbstractNode |
280
|
|
|
* @throws ParentNotFoundException |
281
|
|
|
*/ |
282
|
9 |
|
public function previousSibling(): AbstractNode |
283
|
|
|
{ |
284
|
9 |
|
if (is_null($this->parent)) { |
285
|
3 |
|
throw new ParentNotFoundException('Parent is not set for this node.'); |
286
|
|
|
} |
287
|
|
|
|
288
|
6 |
|
return $this->parent->previousChild($this->id); |
289
|
|
|
} |
290
|
|
|
|
291
|
|
|
/** |
292
|
|
|
* Gets the tag object of this node. |
293
|
|
|
* |
294
|
|
|
* @return Tag |
295
|
|
|
*/ |
296
|
258 |
|
public function getTag(): Tag |
297
|
|
|
{ |
298
|
258 |
|
return $this->tag; |
299
|
|
|
} |
300
|
|
|
|
301
|
|
|
/** |
302
|
|
|
* A wrapper method that simply calls the getAttribute method |
303
|
|
|
* on the tag of this node. |
304
|
|
|
* |
305
|
|
|
* @return array |
306
|
|
|
*/ |
307
|
6 |
|
public function getAttributes(): array |
308
|
|
|
{ |
309
|
6 |
|
$attributes = $this->tag->getAttributes(); |
310
|
6 |
|
foreach ($attributes as $name => $info) { |
311
|
3 |
|
$attributes[$name] = $info['value']; |
312
|
|
|
} |
313
|
|
|
|
314
|
6 |
|
return $attributes; |
315
|
|
|
} |
316
|
|
|
|
317
|
|
|
/** |
318
|
|
|
* A wrapper method that simply calls the getAttribute method |
319
|
|
|
* on the tag of this node. |
320
|
|
|
* |
321
|
|
|
* @param string $key |
322
|
|
|
* @return mixed |
323
|
|
|
*/ |
324
|
195 |
|
public function getAttribute(string $key) |
325
|
|
|
{ |
326
|
195 |
|
$attribute = $this->tag->getAttribute($key); |
327
|
195 |
|
if ( ! is_null($attribute)) { |
328
|
99 |
|
$attribute = $attribute['value']; |
329
|
|
|
} |
330
|
|
|
|
331
|
195 |
|
return $attribute; |
332
|
|
|
} |
333
|
|
|
|
334
|
|
|
/** |
335
|
|
|
* A wrapper method that simply calls the hasAttribute method |
336
|
|
|
* on the tag of this node. |
337
|
|
|
* |
338
|
|
|
* @param string $key |
339
|
|
|
* @return bool |
340
|
|
|
*/ |
341
|
84 |
|
public function hasAttribute(string $key): bool |
342
|
|
|
{ |
343
|
84 |
|
return $this->tag->hasAttribute($key); |
344
|
|
|
} |
345
|
|
|
|
346
|
|
|
/** |
347
|
|
|
* A wrapper method that simply calls the setAttribute method |
348
|
|
|
* on the tag of this node. |
349
|
|
|
* |
350
|
|
|
* @param string $key |
351
|
|
|
* @param string|null $value |
352
|
|
|
* @return AbstractNode |
353
|
|
|
* @chainable |
354
|
|
|
*/ |
355
|
21 |
|
public function setAttribute(string $key, $value): AbstractNode |
356
|
|
|
{ |
357
|
21 |
|
$this->tag->setAttribute($key, $value); |
358
|
|
|
|
359
|
|
|
//clear any cache |
360
|
21 |
|
$this->clear(); |
361
|
|
|
|
362
|
21 |
|
return $this; |
363
|
|
|
} |
364
|
|
|
|
365
|
|
|
/** |
366
|
|
|
* A wrapper method that simply calls the removeAttribute method |
367
|
|
|
* on the tag of this node. |
368
|
|
|
* |
369
|
|
|
* @param string $key |
370
|
|
|
* @return void |
371
|
|
|
*/ |
372
|
3 |
|
public function removeAttribute(string $key): void |
373
|
|
|
{ |
374
|
3 |
|
$this->tag->removeAttribute($key); |
375
|
|
|
|
376
|
|
|
//clear any cache |
377
|
3 |
|
$this->clear(); |
378
|
3 |
|
} |
379
|
|
|
|
380
|
|
|
/** |
381
|
|
|
* A wrapper method that simply calls the removeAllAttributes |
382
|
|
|
* method on the tag of this node. |
383
|
|
|
* |
384
|
|
|
* @return void |
385
|
|
|
*/ |
386
|
3 |
|
public function removeAllAttributes(): void |
387
|
|
|
{ |
388
|
3 |
|
$this->tag->removeAllAttributes(); |
389
|
|
|
|
390
|
|
|
//clear any cache |
391
|
3 |
|
$this->clear(); |
392
|
3 |
|
} |
393
|
|
|
/** |
394
|
|
|
* Function to locate a specific ancestor tag in the path to the root. |
395
|
|
|
* |
396
|
|
|
* @param string $tag |
397
|
|
|
* @return AbstractNode |
398
|
|
|
* @throws ParentNotFoundException |
399
|
|
|
*/ |
400
|
6 |
|
public function ancestorByTag(string $tag): AbstractNode |
401
|
|
|
{ |
402
|
|
|
// Start by including ourselves in the comparison. |
403
|
6 |
|
$node = $this; |
404
|
|
|
|
405
|
6 |
|
while ( ! is_null($node)) { |
406
|
6 |
|
if ($node->tag->name() == $tag) { |
407
|
3 |
|
return $node; |
408
|
|
|
} |
409
|
|
|
|
410
|
3 |
|
$node = $node->getParent(); |
411
|
|
|
} |
412
|
|
|
|
413
|
3 |
|
throw new ParentNotFoundException('Could not find an ancestor with "'.$tag.'" tag'); |
414
|
|
|
} |
415
|
|
|
|
416
|
|
|
/** |
417
|
|
|
* Find elements by css selector |
418
|
|
|
* |
419
|
|
|
* @param string $selector |
420
|
|
|
* @param int $nth |
421
|
|
|
* @return array|AbstractNode |
422
|
|
|
*/ |
423
|
186 |
|
public function find(string $selector, int $nth = null) |
424
|
|
|
{ |
425
|
186 |
|
$selector = new Selector($selector); |
426
|
186 |
|
$nodes = $selector->find($this); |
427
|
|
|
|
428
|
186 |
|
if ( ! is_null($nth)) { |
429
|
|
|
// return nth-element or array |
430
|
186 |
|
if (isset($nodes[$nth])) { |
431
|
114 |
|
return $nodes[$nth]; |
432
|
|
|
} |
433
|
|
|
|
434
|
156 |
|
return null; |
435
|
|
|
} |
436
|
|
|
|
437
|
51 |
|
return $nodes; |
|
|
|
|
438
|
|
|
} |
439
|
|
|
|
440
|
|
|
/** |
441
|
|
|
* Find node by id |
442
|
|
|
* |
443
|
|
|
* @param int $id |
444
|
|
|
* @return bool|AbstractNode |
445
|
|
|
*/ |
446
|
9 |
|
public function findById(int $id) |
447
|
|
|
{ |
448
|
9 |
|
$finder= new Finder($id); |
449
|
|
|
|
450
|
9 |
|
return $finder->find($this); |
451
|
|
|
} |
452
|
|
|
|
453
|
|
|
|
454
|
|
|
/** |
455
|
|
|
* Gets the inner html of this node. |
456
|
|
|
* |
457
|
|
|
* @return string |
458
|
|
|
*/ |
459
|
|
|
abstract public function innerHtml(): string; |
460
|
|
|
|
461
|
|
|
/** |
462
|
|
|
* Gets the html of this node, including it's own |
463
|
|
|
* tag. |
464
|
|
|
* |
465
|
|
|
* @return string |
466
|
|
|
*/ |
467
|
|
|
abstract public function outerHtml(): string; |
468
|
|
|
|
469
|
|
|
/** |
470
|
|
|
* Gets the text of this node (if there is any text). |
471
|
|
|
* |
472
|
|
|
* @return string |
473
|
|
|
*/ |
474
|
|
|
abstract public function text(): string; |
475
|
|
|
|
476
|
|
|
/** |
477
|
|
|
* Call this when something in the node tree has changed. Like a child has been added |
478
|
|
|
* or a parent has been changed. |
479
|
|
|
* |
480
|
|
|
* @return void |
481
|
|
|
*/ |
482
|
|
|
abstract protected function clear(): void; |
483
|
|
|
|
484
|
|
|
/** |
485
|
|
|
* Check is node type textNode |
486
|
|
|
* |
487
|
|
|
* @return boolean |
488
|
|
|
*/ |
489
|
9 |
|
public function isTextNode(): bool |
490
|
|
|
{ |
491
|
|
|
|
492
|
9 |
|
return false; |
493
|
|
|
} |
494
|
|
|
} |
495
|
|
|
|
This check looks for assignments to scalar types that may be of the wrong type.
To ensure the code behaves as expected, it may be a good idea to add an explicit type cast.